Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LOAD
    -0.69
    igan
    -0.68
     inequ
    -0.65
     Reconstruction
    -0.63
     circumstance
    -0.61
     Organ
    -0.60
    FUN
    -0.59
     Fusion
    -0.59
     Amb
    -0.59
    ophon
    -0.59
    POSITIVE LOGITS
    retty
    0.87
    rontal
    0.79
    phabet
    0.79
    quished
    0.74
     Notting
    0.74
    igers
    0.73
     conferences
    0.71
    orers
    0.70
     tongues
    0.68
     finally
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.